{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:53:24Z","timestamp":1777658004435,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446343","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11236-11240","source":"Crossref","is-referenced-by-count":13,"title":["Extending Large Language Models for Speech and Audio Captioning"],"prefix":"10.1109","author":[{"given":"Changli","family":"Tang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}]},{"given":"Wenyi","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}]},{"given":"Guangzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}]},{"given":"Xianzhao","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Tian","family":"Tan","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Lu","family":"Lu","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref2","article-title":"PaLM 2 technical report","author":"Rohan","year":"2023"},{"key":"ref3","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref5","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref6","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref7","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447605"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref10","article-title":"X-LLM: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref12","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref13","article-title":"Listen, think, and understand","author":"Gong","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref15","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023"},{"key":"ref16","article-title":"Macaw-llm: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023"},{"key":"ref17","article-title":"Bubogpt: Enabling visual grounding in multi-modal llms","author":"Zhao","year":"2023"},{"key":"ref18","article-title":"Music understanding LLaMA: Advancing text-to-music generation with question answering and captioning","author":"Liu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746601"},{"key":"ref20","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref21","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref22","article-title":"ESB: A benchmark for multi-domain end-to-end speech recognition","author":"Gandhi","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref24","article-title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face","author":"Shen","year":"2023"},{"key":"ref25","article-title":"AudioGPT: Understanding and generating speech, music, sound, and talking head","author":"Huang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref27","article-title":"WhisperAT: Noise-robust automatic speech recognizers are also strong general audio event taggers","volume-title":"Proc. Interspeech","author":"Gong"},{"key":"ref28","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT","author":"Kim"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446343.pdf?arnumber=10446343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:38:47Z","timestamp":1722573527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446343","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}